no code implementations • 3 Jan 2023 • Daiyu Zhang, Ju-Chiang Wang, Katerina Kosta, Jordan B. L. Smith, Shicen Zhou
Experiments for Chinese lyric-to-melody generation show that the proposed framework is able to model key characteristics of rhythm and pitch distributions in the dataset, and in a subjective evaluation, the melodies generated by our system were rated as similar to or better than those of a state-of-the-art alternative.